ProofPay MCP Server
Provides Solana Pay invoice creation, payment verification, and artifact release tools for ZeroClaw agents, enabling custody-minimized paid delivery of sealed artifacts while keeping encryption keys and policy operator-owned.
README
ProofPay
ProofPay is a custody-minimized paid-delivery primitive for ZeroClaw. An agent can create a Solana Pay invoice, verify an exact finalized SPL-token payment, and release an AES-256-GCM sealed artifact.
The model never receives encryption keys and cannot choose the recipient, mint, RPC, file roots, token decimals, or amount ceiling. Those remain operator-owned TOML policy.
MCP surface
proofpay__create_invoice(artifact_name, amount, buyer_label?)proofpay__invoice_status(invoice_id)proofpay__release_artifact(invoice_id)— writes the verified plaintext locally and returns paid UTF-8 content inline when it is within the operator cap.
Payment rule
A payment is accepted only when a finalized transaction includes the per-invoice reference and an exact configured-mint balance delta for the configured recipient. A reference touch, wrong mint, wrong recipient, underpayment, overpayment, failed transaction, or non-finalized transaction fails closed.
Quick start
python3.12 -m venv .venv
.venv/bin/pip install -e '.[dev]'
cp examples/proofpay.toml proofpay.local.toml
# Replace paths and recipient in proofpay.local.toml.
.venv/bin/proofpay-mcp --config proofpay.local.toml
Run the test suite:
.venv/bin/python -m pytest tests -q
The stdio integration test launches the actual MCP subprocess, initializes a client session, lists the three tools, and creates an invoice. The production-shaped ZeroClaw receipt is in docs/zeroclaw-v0.8.4-receipt.json; the labeled synthetic paid-release receipt is in docs/demo-receipt.json; the optional real-chain harness is documented in docs/DEVNET_SMOKE.md.
ZeroClaw
Install ZeroClaw, then merge examples/zeroclaw-config-snippet.toml into its config and grant the revenue MCP bundle only to the intended agent. Copy skills/proofpay/SKILL.md into that agent's skill bundle.
zeroclaw --version
zeroclaw --config-dir /path/to/config status
ProofPay has been exercised against ZeroClaw v0.8.4's current MCP schema. Absolute paths are intentional: the spawned stdio process must not depend on shell activation.
Architecture
buyer/channel -> ZeroClaw agent -> narrow MCP tools -> ProofPay policy
|-> Solana JSON-RPC
|-> SQLite invoice state
`-> AES-GCM sealed artifact
Security and scope
Read docs/THREAT_MODEL.md before deployment. This prototype handles invoice creation, exact payment verification, and local release. It does not provide buyer authentication, refunds, disputes, tax handling, sanctions screening, or encrypted buyer delivery.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.